← Back to Skills Marketplace
ivangdavila

Basketball

by Iván · GitHub ↗ · v1.0.0 · MIT-0
linuxdarwinwin32 ✓ Security Clean
236
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install basketball
Description
Analyze basketball games, lineups, players, and practice plans with film-room structure, scouting grids, and possession-based coaching tools.
README (SKILL.md)

When to Use

Use this for basketball work: game prep, post-game review, lineup fit, player scouting, role definition, shot-profile discussion, and weekly practice planning.

Do not use it for betting picks, medical advice, fake live stats, or American-football questions. This skill is for usable basketball decisions, not sports chatter.

Architecture

Memory lives in ~/basketball/. If ~/basketball/ does not exist, run setup.md. See memory-template.md for structure.

~/basketball/
├── memory.md          # Activation rules, level, style, and durable preferences
├── possession-map.md  # Recent game plans, reviews, and possession themes
├── roster-notes.md    # Lineups, roles, pairings, and scouting conclusions
├── practice-log.md    # Weekly rhythms, constraints, and drill notes
└── archive/           # Retired reports and old cycles

Quick Reference

Use the smallest file that resolves the blocker.

Topic File
Setup and activation behavior setup.md
Memory and local file templates memory-template.md
Film-room and game-review workflow possession-map.md
Opponent scout template opponent-scout.md
Player evaluation rubric scouting-grid.md
Practice planning and drill logic practice-week.md
Role and lineup fit logic lineup-cards.md

Requirements

  • No credentials required
  • No extra binaries required
  • Persistent notes only after the user approves local memory
  • Ask which level matters: youth, high school, academy, college, rec league, semi-pro, or professional

Data Storage

Local notes in ~/basketball/ may include:

  • activation rules and the situations where basketball help should appear
  • level, region, offensive style, defensive scheme, and analysis preferences
  • recurring opponents, player-role notes, and roster needs
  • weekly practice constraints such as court time, roster size, minutes, and schedule

Keep memory lean. Store durable context that improves future basketball work, not every game note.

Possession Map Protocol

Run the full workflow in possession-map.md. Every basketball task should first be classified into one of these lanes:

Lane Primary output Anchor file
Game preview plan, matchups, counters, focus possessions opponent-scout.md
Post-game review what repeated, why, next fixes possession-map.md
Player scouting role fit, strengths, risk, projection scouting-grid.md
Roster design lineup balance, shot diet, role clarity lineup-cards.md
Practice week microcycle, drill goals, constraints practice-week.md

Default output should be usable in a locker room, staff meeting, film session, or workout block.

Core Rules

1. Lock the Basketball Context Before Giving Advice

  • Confirm the task is basketball, then lock level, ruleset, roster reality, schedule, and decision needed.
  • Advice that ignores level, player availability, and game format sounds smart but fails in real gyms.

2. Separate Observation, Inference, and Recommendation

  • State what is known from film, stats, or user notes before jumping to conclusions.
  • Label assumptions when evidence is partial, stale, or anecdotal.

3. Read the Game Possession by Possession

  • Structure previews and reviews around transition, early offense, half-court creation, defensive shell, rebounding, and special situations.
  • One hot quarter, one made run, or one highlight play rarely explains the actual game.

4. Judge Players Through Roles and Lineup Context

  • Evaluate what a player must solve on offense and defense, which lineup unlocks them, and what cover they need.
  • Good basketball analysis explains fit, spacing, and matchup trade-offs instead of handing out vague labels.

5. Make Practice Match the Real Game Problem

  • Every practice plan needs one clear objective, player numbers, space, timing, drill constraints, coaching cues, and a progression or regression.
  • Sessions that do not map back to the next game or development need become empty reps.

6. End With Coach-Ready Outputs

  • Finish with decisions that matter now: matchup plan, lineup tweak, shot-profile priority, coverage adjustment, or next practice blueprint.
  • If the answer cannot be used by a coach, analyst, scout, or player in under five minutes, tighten it.

7. Respect Basketball Boundaries

  • Do not invent live stats, injuries, or lineup certainty.
  • Do not give betting picks, medical clearance, or fake precision that the evidence cannot support.

Common Traps

These are the failure patterns that most often turn basketball analysis into commentary with no coaching value.

Trap Why It Fails Better Move
Treating every roster like a pro team Youth and amateur groups have different spacing, shooting, and time limits Scale the plan to real talent, court time, and teaching bandwidth
Confusing points scored with process quality Hot shooting can hide bad spacing, turnover risk, or defensive leaks Track shot profile, turnover pressure, paint touches, and second-chance control
Judging players from box scores alone Box scores hide screen quality, low-man help, spacing gravity, and decision speed Use the role lens in scouting-grid.md
Writing practices with no constraints Good drills fail when numbers, timing, or court space do not fit Specify players, area, timing, and scoring constraints every time
Fixing offense while breaking defense More spacing or pace can expose rebounding and transition cover State the trade-off and the cover needed
Using lineup names instead of functional roles "Small ball" or "two-big" labels do not explain what actions actually work Describe creation, spacing, rim pressure, point-of-attack defense, and rebounding jobs

Security & Privacy

Data that leaves your machine:

  • none by default
  • if the user explicitly asks for public basketball facts, only the needed searches, source fetches, or tool calls for that task

Data that stays local:

  • approved basketball notes in ~/basketball/

This skill does NOT:

  • store account credentials or betting logins
  • make undeclared network requests
  • present guesses as verified game data
  • persist local notes without user approval

Scope

This skill ONLY:

  • structures basketball analysis, scouting, roster planning, and practice design
  • turns vague basketball questions into reusable reports and gym-ready outputs
  • stores lightweight local basketball notes after user approval
  • stays inside basketball unless the user clearly redirects

This skill NEVER:

  • place bets, recommend stakes, or act like an odds tool
  • diagnose injuries or clear return-to-play decisions
  • pretend one stat line is enough evidence
  • modify its own skill files

Related Skills

Install with clawhub install \x3Cslug> if user confirms:

  • analysis - structure trade-offs, assumptions, and decision quality.
  • coach - sharpen communication, accountability, and behavior change with players or staff.
  • fitness - handle load, conditioning, and habit work when the conversation shifts beyond tactics.
  • in-depth-research - run source-backed league, opponent, or rules research when facts matter.
  • data-analysis - turn spreadsheets, tracking exports, and dashboards into clearer basketball conclusions.

Feedback

  • If useful: clawhub star basketball
  • Stay updated: clawhub sync
Usage Guidance
This skill appears coherent and low-risk for its stated purpose, but consider these points before enabling persistent memory: 1) Memory is stored locally in ~/basketball/ — review and inspect any files the skill creates and delete them if you no longer want them; 2) Do not store sensitive personal data (passwords, private medical records, private video files) in the skill's notes; the skill itself says not to, but it cannot enforce that for user-provided content; 3) If you prefer no persistence, decline the memory prompt and use the skill session-only; 4) Ask the publisher or maintainer to clarify the minor metadata mismatch (SKILL.md lists a config path while registry metadata shows none) if that concerns you; 5) Autonomous invocation is allowed by default on the platform — that is normal for skills and not a red flag here, but you can limit the skill's use by not enabling persistent triggers or by declining proactive activation settings.
Capability Analysis
Type: OpenClaw Skill Name: basketball Version: 1.0.0 The basketball skill bundle is a well-structured set of templates and instructions designed for basketball coaching, scouting, and practice planning. It utilizes a local directory (~/basketball/) for persistent memory, which is a standard pattern for OpenClaw skills, and explicitly requires user approval before storing data. There is no evidence of malicious intent, data exfiltration, or suspicious command execution; the instructions in SKILL.md and setup.md are focused entirely on maintaining domain-specific context and safety boundaries (e.g., explicitly forbidding betting or medical advice).
Capability Assessment
Purpose & Capability
The name, description, and all included files are consistent: coaching, scouting, practice planning, and possession-based analysis. One minor inconsistency: SKILL.md metadata advertises a config path (~/basketball/) while the registry metadata at the top lists no required config paths — functionally the skill expects a local folder for memory, which is reasonable for this purpose.
Instruction Scope
Runtime instructions focus on basketball workflows and local note templates. They instruct the agent to create/read/write files in ~/basketball/ for persistent memory only after user approval. There are no instructions to access unrelated files, environment variables, external endpoints, or to exfiltrate data.
Install Mechanism
No install spec and no code files beyond documentation: lowest-risk model. Nothing will be downloaded or written automatically unless the user explicitly permits creation of the local memory directory and files.
Credentials
The skill requests no environment variables, no credentials, and no external tokens. This is proportionate to a local coaching/analysis tool.
Persistence & Privilege
The skill intends to store optional persistent memory under ~/basketball/. Persistence is explicitly opt-in per the docs and always:false. Users should understand that approving memory grants the skill the ability to create and update files in that directory.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install basketball
  3. After installation, invoke the skill by name or use /basketball
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release with the Possession Map Protocol, scouting grids, and practice blueprints for practical basketball work.
Metadata
Slug basketball
Version 1.0.0
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is Basketball?

Analyze basketball games, lineups, players, and practice plans with film-room structure, scouting grids, and possession-based coaching tools. It is an AI Agent Skill for Claude Code / OpenClaw, with 236 downloads so far.

How do I install Basketball?

Run "/install basketball" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Basketball free?

Yes, Basketball is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Basketball support?

Basketball is cross-platform and runs anywhere OpenClaw / Claude Code is available (linux, darwin, win32).

Who created Basketball?

It is built and maintained by Iván (@ivangdavila); the current version is v1.0.0.

💬 Comments